edoproch/deepseekr1-distilled-llama-70b-ollama – Run with an API on Replicate

edoproch / deepseekr1-distilled-llama-70b-ollama

DeepSeek-R1 distilled on LLaMA3.3 70B and quantized by ollama

Cold

Public
24 runs
A100 (80GB)
Weights
Paper
License

Iterate in playground

Run with an API

Playground API Examples README Versions

Input

Run this model in Node.js with one line of code:

npx create-replicate --model=edoproch/deepseekr1-distilled-llama-70b-ollama

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run edoproch/deepseekr1-distilled-llama-70b-ollama using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "edoproch/deepseekr1-distilled-llama-70b-ollama:492f524178141b96d3039889672dfca9cacf78d4bfe096e5d3523963fdc7efe7",
  {
    input: {
      prompt: "Solve x+3=5",
      temperature: 0.6
    }
  }
);

console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run edoproch/deepseekr1-distilled-llama-70b-ollama using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "edoproch/deepseekr1-distilled-llama-70b-ollama:492f524178141b96d3039889672dfca9cacf78d4bfe096e5d3523963fdc7efe7",
    input={
        "prompt": "Solve x+3=5",
        "temperature": 0.6
    }
)

# The edoproch/deepseekr1-distilled-llama-70b-ollama model can stream output as it's running.
# The predict method returns an iterator, and you can iterate over that output.
for item in output:
    # https://replicate.com/edoproch/deepseekr1-distilled-llama-70b-ollama/api#output-schema
    print(item, end="")

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run edoproch/deepseekr1-distilled-llama-70b-ollama using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "edoproch/deepseekr1-distilled-llama-70b-ollama:492f524178141b96d3039889672dfca9cacf78d4bfe096e5d3523963fdc7efe7",
    "input": {
      "prompt": "Solve x+3=5",
      "temperature": 0.6
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

<think> I need to solve the equation \( x + 3 = 5 \). First, I'll isolate the variable by subtracting 3 from both sides of the equation. This will give me the value of \( x \). </think> To solve the equation \( x + 3 = 5 \), follow these steps: 1. **Subtract 3 from both sides** to isolate the variable \( x \): \[ x + 3 - 3 = 5 - 3 \] 2. **Simplify** both sides: \[ x = 2 \] Therefore, the solution is: \[ x = \boxed{2} \]

{
  "completed_at": "2025-01-30T18:27:13.065517Z",
  "created_at": "2025-01-30T18:22:14.698000Z",
  "data_removed": false,
  "error": null,
  "id": "qnaskaran9rj60cmq1ss93awb0",
  "input": {
    "prompt": "Solve x+3=5",
    "temperature": 0.6
  },
  "logs": null,
  "metrics": {
    "predict_time": 16.364897082,
    "total_time": 298.367517
  },
  "output": [
    "<think>",
    "\n",
    "I",
    " need",
    " to",
    " solve",
    " the",
    " equation",
    " \\(",
    " x",
    " +",
    " ",
    "3",
    " =",
    " ",
    "5",
    " \\",
    ").\n\n",
    "First",
    ",",
    " I",
    "'ll",
    " isolate",
    " the",
    " variable",
    " by",
    " subtract",
    "ing",
    " ",
    "3",
    " from",
    " both",
    " sides",
    " of",
    " the",
    " equation",
    ".\n\n",
    "This",
    " will",
    " give",
    " me",
    " the",
    " value",
    " of",
    " \\(",
    " x",
    " \\",
    ").\n",
    "</think>",
    "\n\n",
    "To",
    " solve",
    " the",
    " equation",
    " \\(",
    " x",
    " +",
    " ",
    "3",
    " =",
    " ",
    "5",
    " \\",
    "),",
    " follow",
    " these",
    " steps",
    ":\n\n",
    "1",
    ".",
    " **",
    "Sub",
    "tract",
    " ",
    "3",
    " from",
    " both",
    " sides",
    "**",
    " to",
    " isolate",
    " the",
    " variable",
    " \\(",
    " x",
    " \\",
    "):\n",
    "   \n",
    "  ",
    " \\",
    "[\n",
    "  ",
    " x",
    " +",
    " ",
    "3",
    " -",
    " ",
    "3",
    " =",
    " ",
    "5",
    " -",
    " ",
    "3",
    "\n",
    "  ",
    " \\",
    "]\n\n",
    "2",
    ".",
    " **",
    "S",
    "implify",
    "**",
    " both",
    " sides",
    ":\n",
    "   \n",
    "  ",
    " \\",
    "[\n",
    "  ",
    " x",
    " =",
    " ",
    "2",
    "\n",
    "  ",
    " \\",
    "]\n\n",
    "Therefore",
    ",",
    " the",
    " solution",
    " is",
    ":\n\n",
    "\\",
    "[\n",
    "x",
    " =",
    " \\",
    "boxed",
    "{",
    "2",
    "}\n",
    "\\",
    "]",
    ""
  ],
  "started_at": "2025-01-30T18:26:56.700620Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream-g.svc.rno2.c.replicate.net/v1/streams/6w523x33yc6vl7t3qxbgeeb7vo5kmvybddnq4es645q2sw33ihyq",
    "get": "https://api.replicate.com/v1/predictions/qnaskaran9rj60cmq1ss93awb0",
    "cancel": "https://api.replicate.com/v1/predictions/qnaskaran9rj60cmq1ss93awb0/cancel"
  },
  "version": "492f524178141b96d3039889672dfca9cacf78d4bfe096e5d3523963fdc7efe7"
}

Generated in

16.4 seconds

Tweak it Share Report

Run time and cost

This model runs on Nvidia A100 (80GB) GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

🚀 Meet DeepSeek-R1 distilled on LLaMA 70B! Unlike other similar models on Replicate, this one has its weights cached, so you don’t have to waste time downloading them every time. ⏳💨

But wait, there’s more! 🎉 It’s also quantized, meaning you get way better efficiency with barely any performance loss. Smarter, faster, and optimized just for you! ⚡🔥